Sustainability and Productivity Enhancement IoT system for Agriculture

AP064 »

The project vision is to create a modulo IoT network that could be easily modified and applied onto various types of farms and greenhouses to help optimize water use, give insights, and impact the health of crops and the surrounding environment. Hence, increase the quality of the product going to the market and reduce the wastes that will contribute to long-term sustainability.
An IoT network will include a master node made of the FPGA Cloud Connectivity Kit, which will be responsible for collecting data from the sensor nodes, communicating with the cloud along with controlling the actuators that will affect a specific crop on the field.
Each Sensor Node will have its own MCU connected with a Soil Moisture and pH Measurement sensor (CN0398), a Volatile Organic Compound (VOC) Detector (CN0395), the Light Recognition System (CN0397), and potentially any other sensors that the customer requests. The data collected from these sensors will be transmitted to the Master node through wired RS485, wireless LoRa, LoRaWAN or other local transmitting methods (depends on specific setup). The moisture data collected will be used to control a watering pump through an isolated Contactor. pH or other soil qualities data can be statistically displayed to give the user insight into what should be adjusted to the fertilizer. Moreover, the VOC and Light data can be used to conditioning airflow in the greenhouse and changing lighting components to provide the best environment for the crops to thrive.
The cloud-based service will be in contact with the master node to connect the user from anywhere around the world to monitoring and controlling their farm. Besides, the cloud is also responsible for updating the system's firmware Over-The-Air (OTA) and store the processed data from the FPGA for further analysis and future improvement.
If time permits, edge computing Machine Learning will also be applied to the master node to automatically control the watering, lighting and air ventilating based on the crop that is being monitored, hence reduce the network bandwidth, contribute to the long-term energy efficiency compared to applications that do most calculating on the cloud. This network can be scaled up with many Master Nodes, each responsible for specific crops in a greenhouse or a farm, connected all together and monitored by the cloud or by a local Grant Master Node. We are expected to test the system on a greenhouse facility in Vietnam after finishing the prototype, which will give us a better insight into how the system operates.
Through the project, besides expecting to learn a heap of new useful knowledge, our team hopes to create a foundation for improving the efficiency of watering and energy usage in agriculture, especially in developing countries such as our hometown Vietnam.

Project Vanguard

AP065 »

We propose to develop an IoT-based device that alerts nearby emergency services and primary contacts when an accident happens. We propose to develop a device using FPGA along with peripherals like an accelerometer, GPS module, and two cameras to alert the officials thereby mitigating the loss.
When a collision occurs the accelerometer sensors detect the drastic malfunction of an accelerometer. As soon as a collision is detected, the recording is stored in memory so the footage can be retrieved and used by the police for further investigation if necessary. Two memory devices will be used to store the recorded video, as soon as 60 minutes are elapsed, the recording continues in another memory device, while the other one gets cleared so that recording shall not be delayed due to the clearing process.
The FPGA along with the sensors comes in a single package(entity) along with two external cameras. The user should plug the device into the battery socket which is made available in every car which will be a power supply for the FPGA device. The user has to connect the cameras with the device and mount the cameras at the apt position which might require a technician to care of the wiring.
On top of this, the data collected from series and video will be relayed to the cloud on which we plan to implement different algorithms to further process data like average speed during the entire course, etc. Also, the video will be further processed using the algorithms on the cloud to determine various aspects which include but are not limited to the severity of accident, possible recognition of number plates.
Disclaimer: The above information describes the basic functioning of the device as a whole. The final product may include extra features and possible optimizations.

Design and Implementation of FPGA Accelerator for Computed Tomography based 3D reconstruction

AP066 »

COMPUTED tomography (CT) is a commonly used methodology that produces 3D images of patients. It allows doctors to non-invasively diagnose various medical problems such as tumors, internal bleeding, and complex fractures. However, high radiation exposure from CT scans raises serious concerns about safety. This has triggered the development of low-dose compressive sensing-based CT algorithms. Instead of traditional algorithms such as the filtered back projection (FBP) , iterative algorithms such as expectation maximization (EM) are used to obtain a quality image with considerably less radiation exposure.
In this proposed work we present a complete and working CT reconstruction system implemented on a server-class node with FPGA coprocessors. It incorporates several FPGA-friendly techniques for acceleration. The contributions of the proposed work includes:
• Ray-driven voxel-tile parallel approach: This approach exploits the computational simplicity of the ray-driven approach, while taking advantage of both ray and voxel data reuse. Both the race condition and the bank conflict problems are completely removed. Also easily increase the degree of parallelism with adjustment of tile shape.
• Variable throughput matching optimization: Strategies to increase the performance for designs that have a variable and disproportionate throughput rate between processing elements. In particular, the logic consumption is reduced by exploiting the low complexity of frequently computed parts of the ray-driven approach. The logic usage is further reduced by using small granularity PEs and module reuse.
• Offline memory analysis for irregular access patterns in the ray-driven approach: To efficiently tile the voxel for irregular memory access, an offline memory analysis technique is proposed. It exploits the input data independence property of the CT machine and also a compact storage format is presented.
• Customized PE architecture:
We present a design that achieves high throughput and logic reuse for each PE.
• Design flow for rapid hardware-software design:
A flow is presented to generate hardware and software for various CT parameters. In this work we adapt the parallelization scheme, offline memory analysis technique, variable throughput optimization, and the automated design flow. Hence the new optimization would be expected to be much faster than earlier model with same dataset.

DEVELOPMENT OF MULTIPLE MOBILE ROBOTS FOR HEALTHCARE APPLICATIONS USING FPGA

AP068 »

The purpose of our project is to describe the implementation of a “Multiple Mobile Robots” (MMR) that plans and controls the execution of logistics tasks by a set of mobile robots in a real-world hospital environment. The MMR is developed upon an architecture that hosts a routing engine, a supervisor module, controllers and a cloud service. The routing engine handles the geo-referenced data and the calculation of routes; the supervisor module implements algorithms to solve the task allocation problem and the trolley loading problem a temporal estimation of the robot’s positions at any given time hence the robot’s movements are synchronized. Cloud service provides a messaging system to exchange information with the robotic fleet, while the controller implements the control rules to ensure the execution of the work plan on individual robots. The proposed MMR has been developed to have a safe, efficient, and integrated indoor robotic fleets for logistic applications in healthcare and commercial spaces. Moreover, a computational analysis is performed using a virtual hospital floor-plant.

FFPCAM - Forest Fire Prediction & Conservation by Aerial Monitoring

AP069 »

According to NIFC, in 2018, a total of 8,054 wildfires occurred in California, which led to the burning of 1.8 million acres.
The 2019–2020 bushfire season in Australia caused the burning of over 46 million acres of forest while destroying over 10,000 structures.

The project intends to produce the Fire Forecasting capabilities using Deep Learning and develop further improvements in accuracy, geography, and time scale through the inclusion of additional variables or optimization of model architecture & hyperparameters to conserve and sustain forests for the future.

The data acquired from the sensors is processed by the Intel FPGA by the implemented Deep Learning Algorithm and is sent to the connected Azure-based cloud-server which will store real-time data of the factors and will transmit them to our model. The model will then analyze and produce results to be uploaded back to the cloud.

The smart irrigation system that reduces water use in agricultural areas

EM020 »

Introduction

Since only 3% of the world's water is usable by humans and other living things, it is necessary to be more sensitive in this regard. According to the article published by Worldbank in 2017, it was mentioned that approximately 40% of the world's population lives in water-restricted areas, and it is estimated that approximately 1.8 billion people will live in areas without water by 2025 [1]. Therefore, we should use water resources more efficiently. Abundant use of water in agriculture will create major drought problems in the future. According to the Worldbank, a 60% increase in agriculture is required to feed 9 billion people by 2050, which will increase water use by 15% [1]. According to the CUESA (Center for Urban Education about Sustainable Agriculture), it is mentioned that in order to prevent excessive water use in agriculture, farmers should monitor the weather conditions regularly, while at the same time, the moisture level on the soil and plant should be measured continuously. It is stated that a system to be created by monitoring these values will save water usage [2].

Project Design

In our project, we are planning to develop a system that will reduce water use in an agricultural area. While this system will constantly measure the moisture content in the soil, it will also have a structure that will stop the irrigation system from working in case of rain. We will use the CN-0398 coded soil moisture measurement system to measure the humidity level. In addition, we will check whether it is raining with the HL-83 rain sensor. We plan to reduce unnecessary water use by combining these two systems. After analyzing whether the soil needs water or not, we plan to control the irrigation level by sending the necessary data to the cloud system with the ESP8266 Wi-Fi module in order to analyze the last year’s data. We aim to make a measurement every 10 seconds by the system and to send information about the analysis made according to these measurements to the cloud system in less than 5 seconds. Analyzes will be made with the DE10-Nano Kit.

Expected sustainability results and projected resource savings:

The threat of extinction of the world's waters is a very important problem for sustainability. We think that this project will make significant contributions to sustainability. According to a report published in Nature World News, 30% to 50% water savings were made with the smart irrigation system [3]. We plan to save at least 20% of water in irrigation in agriculture. We believe that thousands of tons of water can be saved if the system is started to be used actively in agricultural areas.

References:

[1] “Water resources management,” World Bank. [Online]. Available: https://www.worldbank.org/en/topic/waterresourcesmanagement. [Accessed: 19-Sep-2021].

[2] “10 ways farmers are saving water,” CUESA, 30-Jun-2021. [Online]. Available: https://cuesa.org/article/10-ways-farmers-are-saving-water. [Accessed: 22-Sep-2021].

[3] M. Brown, “Smart irrigation System 'listens' to Plants cries to reduce water use up to 50%,” Nature World News, 03-Sep-2021. [Online]. Available: https://www.natureworldnews.com/articles/47332/20210903/responsive-drip-irrigation-irrigation-system.htm. [Accessed: 23-Sep-2021].

基于FPGA的老年人防跌倒系统的实现

PR037 »

项目主要以FPGA为核心控制系统，通过三轴加速度传感器实时监测老人的运动状态，当老人发生跌倒后，在一定的时间内老人没有通过按键重置系统后，系统将通过GPS系统获取老人当前位置信息，通过GPRS系统呼叫紧急联系人，并且将位置信息通知短信形式发送给其紧急联系人。

Gesture Controlled Robotic Gripper Arm through Kinect Sensor

AP073 »

There are many hazardous tasks that human needs to perform and they are dangerous to do by oneself. our product allows the user to control a robotic gripper arm through kinect sensor, which provides better control and more freedom to the user in a real time environment. This allow us humans to complete these risky operations without endangering ourselves. We designed this project to be helpful in both industrial and medical fields. The idea of the project is to design a robotic gripper arm which is controlled through gestures. The robotic arm will be controlled through a Kinect sensor connected to a PC. The robotic structure will mirror the hand and elbow movements of an actual arm as captured by the Kinect sensor.The goal of the project is to create a robot arm that fully replicates the movement of another hand and arm, and can help one remotely grip and lift an object. In this project, real-time interaction among environment, man, and machine is developed through the machine vision system and the robotic arm.

Sign Language Interpreter

AP074 »

It has two robotic hands along with arms which will work as a sign language interpreter. Sign language interpreter helps people to communicate with the people who are born deaf or have hearing loss. Over 5% of the world's population or 430 million people are facing hearing loss (432 million adults and 34 million children). It is estimated that by 2050 over 700 million people (one in every ten people) will have disabling hearing loss. So, it will be necessary to find ways to communicate with such people. Our sign language interpreter will be able to perform maximum 40-50 signs which includes words and greetings (i.e. hello, goodbye) on the basis of input given by mobile application. By this we can make communication between a normal person and a deaf person easier. For instance, a person wants to communicate with a person who can’t hear. And the person also don’t know the sign language. In that case, he/she can simply give its input to the mobile application and the robotic arm will communicate his/her message to the deaf by performing the sign language.

IOT based agriculture monitoring systems

AP076 »

Agriculture has been one of the primary occupations of man since early civilizations and even today manual interventions in farming are inevitable. There are many plants that are very sensitive to water levels and required specific level of water supply for proper growth, if this not they may die or results in improper growth. It’s hardly possible that every farmer must possess the perfect knowledge about growing specifications of plants in case of water supply. So, to have a help, an attempt is made by introducing the proposed project named Smart Sensors Based Monitoring System for Agriculture Using FPGA. Water saving, improvement in agricultural yield and automation in agriculture are the objectives of this project. By the use of sensors in project, awareness about changing conditions of moisture, temperature and humidity level will be made available for the farmers so that according to changing conditions of moisture, temperature and humidity farmers will be able to schedule the proper timing for water supply and all the necessary things that required for proper growth of plants. This system can also be used in greenhouses to control important parameters like temperature, soil moisture, humidity etc as per the requirement of proper growth of plants.

Image Reconstruction Using FPGA for Adaptive Vehicle Systems

AP077 »

AUTONOMOUS CAR - A SELF DRIVING CAR INTEGRATED WITH DETECTIONS

AP078 »

World Health Organization (WHO) reports 1.35 million people deaths in car accidents every year, and hence this is an issue of serious concern. Deaths/Serious injuries in car accidents effects the families of the individuals completely for their life time. As per the observations, the primary causes of these accidents are cellphone usage while driving, over speed, violation of traffic rules, alcoholic consumptions, bad weather conditions etc., most of these causes of accidents may be reduced, if manual operation of vehicle is reduced to the maximum possible extent.
It is already known that, a lot of research work is going on across the globe on design of autonomous vehicles/self-driving cars/driverless cars and few of them may become a reality soon on the roads. But, this technology will be appreciated when it will work with maximum efficiency and simultaneously when it is made available to the general public even.
In our proposal, we would like to design a prototype of self-driving car which uses machine learning algorithms and will fulfill the following objectives:
1) Collision warning system
2) Movement of vehicle not only during day-time but also during night time and during bad weather conditions
3) GPS based routing of vehicle
4) Lane detection
5) Object/obstacle detection
We, would like to use the features present in the FPGA platform for efficient working of the prototype. In our proposed design, we will be using DE-10 Nano FPGA board, Adasky viper(for input), 2 motor shields (cryton)(for controlling car speed), 12V battery(to energize car) and Arduino UNOcomponents.